Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    σ
    -0.06
    "+"
    -0.06
    VERTISE
    -0.06
    Actions
    -0.06
    国の
    -0.06
    ıl
    -0.06
    arius
    -0.06
    كييف
    -0.06
    "]==
    -0.06
    -HT
    -0.06
    POSITIVE LOGITS
    Remember
    0.06
     obec
    0.06
     Medicare
    0.06
     Vocal
    0.06
    (Boolean
    0.06
    _SAFE
    0.06
    .Document
    0.06
    -Encoding
    0.06
    .Enabled
    0.06
     Congo
    0.06
    Act Density 0.000%

    No Known Activations